How some skills become second nature
Patterns of gaze and attention can reveal how some people unconsciously figure out how to master a task, new research shows.
Archives AI News
Gauge Flow Models
arXiv:2507.13414v3 Announce Type: replace Abstract: This paper introduces Gauge Flow Models, a novel class of Generative Flow Models. These models incorporate a learnable Gauge Field within the Flow Ordinary Differential Equation (ODE). A comprehensive mathematical framework for these models, detailing…
Loss Barcode: A Topological Measure of Escapability in Loss Landscapes
arXiv:2012.15834v3 Announce Type: replace Abstract: Neural network training is commonly based on SGD. However, the understanding of SGD’s ability to converge to good local minima, given the non-convex nature of loss functions and the intricate geometric characteristics of loss landscapes,…
Know When to Abstain: Optimal Selective Classification with Likelihood Ratios
arXiv:2505.15008v3 Announce Type: replace Abstract: Selective classification enhances the reliability of predictive models by allowing them to abstain from making uncertain predictions. In this work, we revisit the design of optimal selection functions through the lens of the Neyman–Pearson lemma,…
CHAMMI-75: Pre-training multi-channel models with heterogeneous microscopy images
arXiv:2512.20833v2 Announce Type: replace-cross Abstract: Quantifying cell morphology using images and machine learning has proven to be a powerful tool to study the response of cells to treatments. However, models used to quantify cellular morphology are typically trained with a…
Variance reduction in lattice QCD observables via normalizing flows
arXiv:2603.02984v1 Announce Type: cross Abstract: Normalizing flows can be used to construct unbiased, reduced-variance estimators for lattice field theory observables that are defined by a derivative with respect to action parameters. This work implements the approach for observables involving gluonic…
MedCalc-Bench Doesn’t Measure What You Think: A Benchmark Audit and the Case for Open-Book Evaluation
arXiv:2603.02222v1 Announce Type: new Abstract: MedCalc-Bench is a widely used benchmark for evaluating LLM performance on clinical calculator tasks, with state-of-the-art direct prompting scores plateauing around 35% on the Verified split (HELM MedHELM leaderboard) and the best published approach-RL with…
Topic-Based Watermarks for Large Language Models
arXiv:2404.02138v5 Announce Type: replace-cross Abstract: The indistinguishability of large language model (LLM) output from human-authored content poses significant challenges, raising concerns about potential misuse of AI-generated text and its influence on future model training. Watermarking algorithms offer a viable solution…
Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting
arXiv:2603.02220v1 Announce Type: new Abstract: Time series forecasting (TSF) remains a challenging problem due to the intricate entanglement of intraperiod-fluctuations and interperiod-trends. While recent advances have attempted to reshape 1D sequences into 2D period-phase representations, they suffer from two principal…
MedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Clinical Tabular Prediction
arXiv:2603.02221v1 Announce Type: new Abstract: In healthcare tabular predictions, classical models with feature engineering often outperform neural approaches. Recent advances in Large Language Models enable the integration of domain knowledge into feature engineering, offering a promising direction. However, existing approaches…